Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    industry news

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Violation
    -0.08
    Broker
    -0.07
     upgrading
    -0.07
     stopping
    -0.07
    _calc
    -0.07
     boats
    -0.07
    +$
    -0.07
     boxer
    -0.07
    ImGui
    -0.07
     withheld
    -0.06
    POSITIVE LOGITS
    (reordered
    0.07
    💒
    0.07
    \Database
    0.07
    我爱你
    0.07
     PERF
    0.06
     unresolved
    0.06
     结
    0.06
    的成本
    0.06
    펀
    0.06
    羼
    0.06
    Act Density 0.027%

    No Known Activations